Deep learning is effective in diagnosing COVID-19 and requires a large amount of data to be effectively trained. Due to data and privacy regulations, hospitals generally have no access to data from other hospitals. Federated learning (FL) has been used to solve this problem, where it utilizes a distributed setting to train models in hospitals in a privacy-preserving manner. Deploying FL is not always feasible as it requires high computation and network communication resources. This paper evaluates five FL algorithms' performance and resource efficiency for Covid-19 detection. A decentralized setting with CNN networks is set up, and the performance of FL algorithms is compared with a centralized environment. We examined the algorithms with varying numbers of participants, federated rounds, and selection algorithms. Our results show that cyclic weight transfer can have better overall performance, and results are better with fewer participating hospitals. Our results demonstrate good performance for detecting COVID-19 patients and might be useful in deploying FL algorithms for covid-19 detection and medical image analysis in general.

翻译：深度学习在诊断COVID-19方面非常有效，但需要大量数据才能有效训练。由于数据与隐私法规的限制，医院通常无法获取其他医院的数据。联邦学习（FL）通过利用分布式设置以隐私保护的方式在医院中训练模型，解决了这一问题。然而，部署联邦学习并不总是可行的，因为它需要较高的计算和网络通信资源。本文评估了五种联邦学习算法在COVID-19检测中的性能与资源效率。我们搭建了基于CNN网络的去中心化设置，并将联邦学习算法的性能与集中式环境进行了比较。我们考察了不同参与者数量、联邦轮次以及选择算法下的算法表现。研究结果表明，循环权重传递具有更优的整体性能，并且当参与医院数量较少时效果更佳。我们的成果展示了在检测COVID-19患者方面的良好性能，且可能有助于联邦学习算法在COVID-19检测及一般医学图像分析中的部署。